What does an interpreter do?

Interpreters convert spoken or sign language statements from one language to another. Interpreting involves listening to, understanding and memorising content in the original ‘source’ language, then reproducing statements, questions and speeches in a different ‘target’ language. This is often done in only one direction, normally into the interpreter’s native language, but may be on a two-way basis. Interpreters facilitate effective communication between clients in the following settings:
•large conferences and formal meetings;
•business functions such as smaller meetings, exhibitions and product launches;
•criminal justice proceedings, known as public service interpreting or PSI, including police and probation service interviews, court hearings, solicitor interviews, arbitration hearings and immigration tribunals;
•community-based events and assignments within the education, health and social services sectors.

Interpreting can be carried out in various ways: person, whether in the same room or from a nearby conference booth; telephone, when the interpreter is in a different location from the speakers;
3.via video conferencing and internet-based technologies.

There are several types of interpreting:

1.Simultaneous interpretation (SI)  Simultaneous interpretation involves working in a team at a conference or large meeting. The interpreter sits in a soundproof booth (there are separate booths for each conference language) and immediately converts what is being said, so listeners hear the interpretation through an earpiece while the speaker is still speaking. A variation of this is whispering, or chuchotage, where the interpreter sits near one person or a small group and whispers the translation as the speaker carries on. Sign language interpreting is also usually simultaneous.

2.Consecutive interpretation (CI) Consecutive interpretation is more common in smaller meetings and discussions. The speaker will pause after each sentence or point and wait while the interpreter translates what is being said into the appropriate language.

3.Liaison interpretation. Liaison interpretation, also known as ad hoc and relay,is a type of two-way interpreting where the interpreter translates every few sentences while the speaker pauses. This is common in telephone interpreting as well as in legal and health situations. The interpreter supports people who are not fluent in the language being used to ensure their understanding.

4.Sign language interpretation.  Sign language interpreters convert spoken statements into sign language and vice versa. Interpreting from one sign language to another is a new area.

The following work activities are likely in any interpreting setting:
•assimilating speakers’ words quickly, including jargon and acronyms;
•analysing sentences expressed in one language and explaining them using another language;
•building up specialist vocabulary banks;
•writing notes to aid memory;
•using microphones and headsets;
•preparing paperwork – considering agendas before meetings, or lectures/speeches when received in advance;
•using the internet to conduct research;
•organising workload and liaising with internal departments, agencies and/or employers;
•working to a professional code of ethics covering confidentiality and impartiality.

by Leslaw Fiutowski


What is machine translation?

What Is Machine Translation?

Machine translation (MT) is automated translation. It is the process by which computer software is used to translate a text from one natural language (such as English) to another (such as Spanish).

To process any translation, human or automated, the meaning of a text in the original (source) language must be fully restored in the target language, i.e. the translation. While on the surface this seems straightforward, it is far more complex. Translation is not a mere word-for-word substitution. A translator must interpret and analyze all of the elements in the text and know how each word may influence another. This requires extensive expertise in grammar, syntax (sentence structure), semantics (meanings), etc., in the source and target languages, as well as familiarity with each local region.

Human and machine translation each have their share of challenges. For example, no two individual translators can produce identical translations of the same text in the same language pair, and it may take several rounds of revisions to meet customer satisfaction. But the greater challenge lies in how machine translation can produce publishable quality translations.

Rule-Based Machine Translation Technology

Rule-based machine translation relies on countless built-in linguistic rules and millions of bilingual dictionaries for each language pair.

The software parses text and creates a transitional representation from which the text in the target language is generated. This process requires extensive lexicons with morphological, syntactic, and semantic information, and large sets of rules. The software uses these complex rule sets and then transfers the grammatical structure of the source language into the target language.

Translations are built on gigantic dictionaries and sophisticated linguistic rules. Users can improve the out-of-the-box translation quality by adding their terminology into the translation process. They create user-defined dictionaries which override the system’s default settings.

In most cases, there are two steps: an initial investment that significantly increases the quality at a limited cost, and an ongoing investment to increase quality incrementally. While rule-based MT brings companies to the quality threshold and beyond, the quality improvement process may be long and expensive.

Statistical Machine Translation Technology

Statistical machine translation utilizes statistical translation models whose parameters stem from the analysis of monolingual and bilingual corpora. Building statistical translation models is a quick process, but the technology relies heavily on existing multilingual corpora. A minimum of 2 million words for a specific domain and even more for general language are required. Theoretically it is possible to reach the quality threshold but most companies do not have such large amounts of existing multilingual corpora to build the necessary translation models. Additionally, statistical machine translation is CPU intensive and requires an extensive hardware configuration to run translation models for average performance levels.

Rule-Based MT vs. Statistical MT

Rule-based MT provides good out-of-domain quality and is by nature predictable. Dictionary-based customization guarantees improved quality and compliance with corporate terminology. But translation results may lack the fluency readers expect. In terms of investment, the customization cycle needed to reach the quality threshold can be long and costly. The performance is high even on standard hardware.

Statistical MT provides good quality when large and qualified corpora are available. The translation is fluent, meaning it reads well and therefore meets user expectations. However, the translation is neither predictable nor consistent. Training from good corpora is automated and cheaper. But training on general language corpora, meaning text other than the specified domain, is poor. Furthermore, statistical MT requires significant hardware to build and manage large translation models.